Preface

Over the last decade, the field of machine learning has taken great strides, and in so doing has captured the public’s imagination. But it’s crucial to remember that – as impressive as these algorithms are – they are not infallible. Through this book, we hope to provide an approachable introduction to how Bayesian inference can be leveraged within deep learning, giving the reader the tools to develop models that ”know when they don’t know.” In so doing, you’ll be able to develop more robust deep learning systems better suited to the demands of today’s machine learning-based applications.

Who this book is for

This book is for researchers, developers, and engineers who work on the development and application of machine learning algorithms, and who want to start working with uncertainty-aware deep learning models.

What this book covers

Chapter 1, Bayesian Inference in the Age of Deep Learning, covers use cases and limitations of traditional deep learning methods.

Chapter 2, Fundamentals of Bayesian Inference, discusses Bayesian modeling and inference and explores gold-standard machine learning methods for Bayesian inference.

Chapter 3, Fundamentals of Deep Learning, introduces you to the main building blocks of deep learning models.

Chapter 4, Introducing Bayesian Deep Learning, combines the concepts introduced in Chapter 2, Fundamentals of Bayesian Inference and Chapter 3, Fundamentals of Deep Learning to discuss Bayesian deep learning.

Chapter 5, Principled Approaches for Bayesian Deep Learning, introduces well-principled methods for Bayesian neural network approximation.

Chapter 6, Using the Standard Toolbox for Bayesian Deep Learning, introduces approaches for facilitating model uncertainty estimation with common deep learning methods.

Chapter 7, Practical Considerations for Bayesian Deep Learning, explores and compares the advantages and disadvantages of the methods introduced in Chapter 5, Principled Approaches for Bayesian Deep Learning and Chapter 6, Using the Standard Toolbox for Bayesian Deep Learning.

Chapter 8, Applying Bayesian Deep Learning, gives a practical overview of a variety of applications of Bayesian Deep Learning, such as detecting out-of-distribution data or robustness against dataset shift.

Chapter 9, Next Steps in Bayesian Deep Learning, discusses some of the latest trends in Bayesian deep learning.

To get the most out of this book

You are expected to have some prior knowledge of machine learning and deep learning, as well as some familiarity with concepts around Bayesian inference. Some practical knowledge of working with Python and a machine learning framework such as TensorFlow or PyTorch would also be valuable but is not necessary.

Python 3.8 or above is recommended, as all code has been tested with Python 3.8. Chapter 1, Bayesian Inference in the Age of Deep Learning provides detailed instructions on setting up your environment for the book’s code examples.

Download the example code files

The code bundle for the book is also hosted on GitHub at https://github.com/PacktPublishing/Enhancing-Deep-Learning-with-Bayesian-Inference. If there is an update to the code, it will be updated on the existing GitHub repository.

We also have other code bundles from our rich catalog of books and videos available at https://github.com/PacktPublishing/. Check them out!

Download the color images

We also provide a PDF file that has color images of the screenshots/diagrams used in this book. You can download it here: https://packt.link/7xy1O.

Conventions used

There are a number of text conventions used throughout this book.

CodeInText: Indicates code words in text, database table names, folder names, filenames, file extensions, pathnames, dummy URLs, and user input. Here is an example: ”Any attempt to run code that has such issues will immediately cause the interpreter to fail, raising a SyntaxError exception.”

A block of code is set as follows:

 
{const set = function(...items) {  
    this.arr  = [...items];  
    this.add = {function}(item) {  
        if( this._arr.includes(item) ) {  
            return false; (SC-Source)}

Any command-line input or output is written as follows:

 
$ python3 script.py

Some code examples will represent the input of shells. You can recognize them by specific prompt characters:

• >>> for interactive Python shell
• $ for Bash shell (macOS and Linux)
• > for CMD or PowerShell (Windows)

Warnings or important notes appear like this.

Important note

Warnings or important notes appear like this.

Tips and tricks appear like this.

Tips or tricks

Appear like this.

Get in touch

Feedback from our readers is always welcome.

General feedback: If you have questions about any aspect of this book, mention the book title in the subject of your message and email us at [e-mail].

Errata: Although we have taken every care to ensure the accuracy of our content, mistakes do happen. If you have found a mistake in this book, we would be grateful if you would report this to us. Please visit www.packtpub.com/submit-errata, selecting your book, clicking on the Errata Submission Form link, and entering the details.

Piracy: If you come across any illegal copies of our works in any form on the Internet, we would be grateful if you would provide us with the location address or website name. Please contact us at [e-mail] with a link to the material.

If you are interested in becoming an author: If there is a topic that you have expertise in and you are interested in either writing or contributing to a book, please visit authors.packtpub.com.

Share Your Thoughts

Once you’ve read Enhancing Deep Learning with Bayesian Inference, we’d love to hear your thoughts! Please click here to go straight to the Amazon review page for this book and share your feedback.

Your review is important to us and the tech community and will help us make sure we’re delivering excellent quality content.

Download a free PDF copy of this book

Thanks for purchasing this book!

Do you like to read on the go but are unable to carry your print books everywhere?

Is your eBook purchase not compatible with the device of your choice?

Don’t worry, now with every Packt book you get a DRM-free PDF version of that book at no cost.

Read anywhere, any place, on any device. Search, copy, and paste code from your favorite technical books directly into your application.

The perks don’t stop there, you can get exclusive access to discounts, newsletters, and great free content in your inbox daily

Follow these simple steps to get the benefits:

1. Scan the QR code or visit the link below

   

   https://packt.link/free-ebook/9781803246888

2. Submit your proof of purchase

3. That’s it! We’ll send your free PDF and other benefits to your email directly